Training in progress, step 75, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44ad15e64db001e1a1f2c3056046232d62594514e98766859f1e00c65346e429
+oid sha256:31e521efde6226b6cade415c1d669ab3822f9f05786ed4ecfd3a13bafb4b358d
 size 335604696

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:633a9737c4ab3dd787211a3bbea56f9f4645571126fe5926f072bc2d33c9f275
+oid sha256:dc88e50551755a1dfa21ea3b195986e8ec9c81e2a7aa7fc6a9b9cee77c445be4
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac5f70442b6e4fba1c726ef7a3d9603c39539e88c7ff2a6e3c8918cc4259c51a
+oid sha256:cfd632e71485515db51ac5385e7799615dbfb92cc6f52fce17c76e4a9f8486d1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46fa8207e86dee7d50b0ab12f1dd18c4426e8c65d06f97f8b2bd004a747e9cfa
+oid sha256:212837ccb433e5430b061dc107b19dc09e932e6cfb62a751187d0903b7b0d94e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04764173415912339,
+  "epoch": 0.07146260123868509,
   "eval_steps": 25,
-  "global_step": 50,
+  "global_step": 75,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -381,6 +381,189 @@
       "eval_samples_per_second": 4.648,
       "eval_steps_per_second": 2.324,
       "step": 50
+    },
+    {
+      "epoch": 0.04859456884230586,
+      "grad_norm": 5.057662487030029,
+      "learning_rate": 2.500000000000001e-05,
+      "loss": 2.1957,
+      "step": 51
+    },
+    {
+      "epoch": 0.04954740352548833,
+      "grad_norm": 2.368539571762085,
+      "learning_rate": 2.3135019582658802e-05,
+      "loss": 2.2245,
+      "step": 52
+    },
+    {
+      "epoch": 0.0505002382086708,
+      "grad_norm": 2.0508615970611572,
+      "learning_rate": 2.132117818244771e-05,
+      "loss": 2.2957,
+      "step": 53
+    },
+    {
+      "epoch": 0.05145307289185326,
+      "grad_norm": 1.9854440689086914,
+      "learning_rate": 1.9561928549563968e-05,
+      "loss": 2.1347,
+      "step": 54
+    },
+    {
+      "epoch": 0.05240590757503573,
+      "grad_norm": 1.7406495809555054,
+      "learning_rate": 1.7860619515673033e-05,
+      "loss": 2.2859,
+      "step": 55
+    },
+    {
+      "epoch": 0.0533587422582182,
+      "grad_norm": 1.5683196783065796,
+      "learning_rate": 1.622048961921699e-05,
+      "loss": 2.342,
+      "step": 56
+    },
+    {
+      "epoch": 0.054311576941400666,
+      "grad_norm": 1.467210292816162,
+      "learning_rate": 1.4644660940672627e-05,
+      "loss": 2.331,
+      "step": 57
+    },
+    {
+      "epoch": 0.055264411624583135,
+      "grad_norm": 1.634995698928833,
+      "learning_rate": 1.3136133159493802e-05,
+      "loss": 2.1551,
+      "step": 58
+    },
+    {
+      "epoch": 0.0562172463077656,
+      "grad_norm": 1.3047391176223755,
+      "learning_rate": 1.1697777844051105e-05,
+      "loss": 2.2066,
+      "step": 59
+    },
+    {
+      "epoch": 0.05717008099094807,
+      "grad_norm": 1.1119383573532104,
+      "learning_rate": 1.0332332985438248e-05,
+      "loss": 2.0849,
+      "step": 60
+    },
+    {
+      "epoch": 0.05812291567413054,
+      "grad_norm": 1.1421319246292114,
+      "learning_rate": 9.042397785550405e-06,
+      "loss": 2.1172,
+      "step": 61
+    },
+    {
+      "epoch": 0.05907575035731301,
+      "grad_norm": 1.152631402015686,
+      "learning_rate": 7.830427709355725e-06,
+      "loss": 2.4149,
+      "step": 62
+    },
+    {
+      "epoch": 0.06002858504049548,
+      "grad_norm": 1.3147021532058716,
+      "learning_rate": 6.698729810778065e-06,
+      "loss": 2.3454,
+      "step": 63
+    },
+    {
+      "epoch": 0.06098141972367794,
+      "grad_norm": 1.3595980405807495,
+      "learning_rate": 5.649458341088915e-06,
+      "loss": 2.0931,
+      "step": 64
+    },
+    {
+      "epoch": 0.06193425440686041,
+      "grad_norm": 2.0441415309906006,
+      "learning_rate": 4.684610648167503e-06,
+      "loss": 2.3878,
+      "step": 65
+    },
+    {
+      "epoch": 0.06288708909004288,
+      "grad_norm": 1.2968662977218628,
+      "learning_rate": 3.8060233744356633e-06,
+      "loss": 2.1372,
+      "step": 66
+    },
+    {
+      "epoch": 0.06383992377322535,
+      "grad_norm": 1.2718733549118042,
+      "learning_rate": 3.0153689607045845e-06,
+      "loss": 2.2646,
+      "step": 67
+    },
+    {
+      "epoch": 0.06479275845640782,
+      "grad_norm": 1.2259955406188965,
+      "learning_rate": 2.314152462588659e-06,
+      "loss": 2.2772,
+      "step": 68
+    },
+    {
+      "epoch": 0.06574559313959027,
+      "grad_norm": 1.2223516702651978,
+      "learning_rate": 1.70370868554659e-06,
+      "loss": 2.2698,
+      "step": 69
+    },
+    {
+      "epoch": 0.06669842782277274,
+      "grad_norm": 1.2529011964797974,
+      "learning_rate": 1.1851996440033319e-06,
+      "loss": 2.2766,
+      "step": 70
+    },
+    {
+      "epoch": 0.06765126250595521,
+      "grad_norm": 1.4887171983718872,
+      "learning_rate": 7.596123493895991e-07,
+      "loss": 2.2977,
+      "step": 71
+    },
+    {
+      "epoch": 0.06860409718913768,
+      "grad_norm": 1.5588957071304321,
+      "learning_rate": 4.277569313094809e-07,
+      "loss": 2.3476,
+      "step": 72
+    },
+    {
+      "epoch": 0.06955693187232015,
+      "grad_norm": 1.3241275548934937,
+      "learning_rate": 1.9026509541272275e-07,
+      "loss": 2.3195,
+      "step": 73
+    },
+    {
+      "epoch": 0.07050976655550262,
+      "grad_norm": 1.6149224042892456,
+      "learning_rate": 4.7588920907110094e-08,
+      "loss": 2.4973,
+      "step": 74
+    },
+    {
+      "epoch": 0.07146260123868509,
+      "grad_norm": 1.5767426490783691,
+      "learning_rate": 0.0,
+      "loss": 2.4994,
+      "step": 75
+    },
+    {
+      "epoch": 0.07146260123868509,
+      "eval_loss": NaN,
+      "eval_runtime": 189.8117,
+      "eval_samples_per_second": 4.657,
+      "eval_steps_per_second": 2.329,
+      "step": 75
     }
   ],
   "logging_steps": 1,
@@ -395,12 +578,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.3782543103741133e+17,
+  "total_flos": 2.1242647625387213e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null